21 files changed, 1085 insertions, 201 deletions

diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 7b4b564961d4..2d145e38ad49 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -9,15 +9,16 @@ AFLAGS_head.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 arm64-obj-y		:= cputable.o debug-monitors.o entry.o irq.o fpsimd.o	\
 			   entry-fpsimd.o process.o ptrace.o setup.o signal.o	\
 			   sys.o stacktrace.o time.o traps.o io.o vdso.o	\
-			   hyp-stub.o psci.o
+			   hyp-stub.o psci.o cpu_ops.o
 
 arm64-obj-$(CONFIG_COMPAT)		+= sys32.o kuser32.o signal32.o 	\
 					   sys_compat.o
 arm64-obj-$(CONFIG_MODULES)		+= arm64ksyms.o module.o
-arm64-obj-$(CONFIG_SMP)			+= smp.o smp_spin_table.o smp_psci.o
+arm64-obj-$(CONFIG_SMP)			+= smp.o smp_spin_table.o
 arm64-obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o
 arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)+= hw_breakpoint.o
 arm64-obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
+arm64-obj-$(CONFIG_ARM_CPU_TOPOLOGY)  += topology.o
 
 obj-y					+= $(arm64-obj-y) vdso/
 obj-m					+= $(arm64-obj-m)
diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c
new file mode 100644
index 000000000000..04efea8fe4bc
--- /dev/null
+++ b/arch/arm64/kernel/cpu_ops.c
@@ -0,0 +1,99 @@
+/*
+ * CPU kernel entry/exit control
+ *
+ * Copyright (C) 2013 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <asm/cpu_ops.h>
+#include <asm/smp_plat.h>
+#include <linux/errno.h>
+#include <linux/of.h>
+#include <linux/string.h>
+
+extern const struct cpu_operations smp_spin_table_ops;
+extern const struct cpu_operations cpu_psci_ops;
+
+const struct cpu_operations *cpu_ops[NR_CPUS];
+
+static const struct cpu_operations *supported_cpu_ops[] __initconst = {
+#ifdef CONFIG_SMP
+	&smp_spin_table_ops,
+	&cpu_psci_ops,
+#endif
+	NULL,
+};
+
+static const struct cpu_operations * __init cpu_get_ops(const char *name)
+{
+	const struct cpu_operations **ops = supported_cpu_ops;
+
+	while (*ops) {
+		if (!strcmp(name, (*ops)->name))
+			return *ops;
+
+		ops++;
+	}
+
+	return NULL;
+}
+
+/*
+ * Read a cpu's enable method from the device tree and record it in cpu_ops.
+ */
+int __init cpu_read_ops(struct device_node *dn, int cpu)
+{
+	const char *enable_method = of_get_property(dn, "enable-method", NULL);
+	if (!enable_method) {
+		/*
+		 * The boot CPU may not have an enable method (e.g. when
+		 * spin-table is used for secondaries). Don't warn spuriously.
+		 */
+		if (cpu != 0)
+			pr_err("%s: missing enable-method property\n",
+				dn->full_name);
+		return -ENOENT;
+	}
+
+	cpu_ops[cpu] = cpu_get_ops(enable_method);
+	if (!cpu_ops[cpu]) {
+		pr_warn("%s: unsupported enable-method property: %s\n",
+			dn->full_name, enable_method);
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+void __init cpu_read_bootcpu_ops(void)
+{
+	struct device_node *dn = NULL;
+	u64 mpidr = cpu_logical_map(0);
+
+	while ((dn = of_find_node_by_type(dn, "cpu"))) {
+		u64 hwid;
+		const __be32 *prop;
+
+		prop = of_get_property(dn, "reg", NULL);
+		if (!prop)
+			continue;
+
+		hwid = of_read_number(prop, of_n_addr_cells(dn));
+		if (hwid == mpidr) {
+			cpu_read_ops(dn, 0);
+			of_node_put(dn);
+			return;
+		}
+	}
+}
diff --git a/arch/arm64/kernel/cputable.c b/arch/arm64/kernel/cputable.c
index 63cfc4a43f4e..fd3993cb060f 100644
--- a/arch/arm64/kernel/cputable.c
+++ b/arch/arm64/kernel/cputable.c
@@ -22,7 +22,7 @@
 
 extern unsigned long __cpu_setup(void);
 
-struct cpu_info __initdata cpu_table[] = {
+struct cpu_info cpu_table[] = {
 	{
 		.cpu_id_val	= 0x000f0000,
 		.cpu_id_mask	= 0x000f0000,
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 1d1314280a03..6ad781b21c08 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -121,7 +121,7 @@
 
 	.macro	get_thread_info, rd
 	mov	\rd, sp
-	and	\rd, \rd, #~((1 << 13) - 1)	// top of 8K stack
+	and	\rd, \rd, #~(THREAD_SIZE - 1)	// top of stack
 	.endm
 
 /*
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index e8b8357aedb4..2fa308e4a1fa 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -79,8 +79,10 @@ void fpsimd_thread_switch(struct task_struct *next)
 
 void fpsimd_flush_thread(void)
 {
+	preempt_disable();
 	memset(&current->thread.fpsimd_state, 0, sizeof(struct fpsimd_state));
 	fpsimd_load_state(&current->thread.fpsimd_state);
+	preempt_enable();
 }
 
 /*
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 53dcae49e729..3532ca613718 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -217,7 +217,6 @@ ENTRY(__boot_cpu_mode)
 	.quad	PAGE_OFFSET
 
 #ifdef CONFIG_SMP
-	.pushsection    .smp.pen.text, "ax"
 	.align	3
 1:	.quad	.
 	.quad	secondary_holding_pen_release
@@ -242,7 +241,16 @@ pen:	ldr	x4, [x3]
 	wfe
 	b	pen
 ENDPROC(secondary_holding_pen)
-	.popsection
+
+	/*
+	 * Secondary entry point that jumps straight into the kernel. Only to
+	 * be used where CPUs are brought online dynamically by the kernel.
+	 */
+ENTRY(secondary_entry)
+	bl	__calc_phys_offset		// x2=phys offset
+	bl	el2_setup			// Drop to EL1
+	b	secondary_startup
+ENDPROC(secondary_entry)
 
 ENTRY(secondary_startup)
 	/*
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index ecb3354292ed..473e5dbf8f39 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -81,3 +81,64 @@ void __init init_IRQ(void)
 	if (!handle_arch_irq)
 		panic("No interrupt controller found.");
 }
+
+#ifdef CONFIG_HOTPLUG_CPU
+static bool migrate_one_irq(struct irq_desc *desc)
+{
+	struct irq_data *d = irq_desc_get_irq_data(desc);
+	const struct cpumask *affinity = d->affinity;
+	struct irq_chip *c;
+	bool ret = false;
+
+	/*
+	 * If this is a per-CPU interrupt, or the affinity does not
+	 * include this CPU, then we have nothing to do.
+	 */
+	if (irqd_is_per_cpu(d) || !cpumask_test_cpu(smp_processor_id(), affinity))
+		return false;
+
+	if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
+		affinity = cpu_online_mask;
+		ret = true;
+	}
+
+	c = irq_data_get_irq_chip(d);
+	if (!c->irq_set_affinity)
+		pr_debug("IRQ%u: unable to set affinity\n", d->irq);
+	else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret)
+		cpumask_copy(d->affinity, affinity);
+
+	return ret;
+}
+
+/*
+ * The current CPU has been marked offline.  Migrate IRQs off this CPU.
+ * If the affinity settings do not allow other CPUs, force them onto any
+ * available CPU.
+ *
+ * Note: we must iterate over all IRQs, whether they have an attached
+ * action structure or not, as we need to get chained interrupts too.
+ */
+void migrate_irqs(void)
+{
+	unsigned int i;
+	struct irq_desc *desc;
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	for_each_irq_desc(i, desc) {
+		bool affinity_broken;
+
+		raw_spin_lock(&desc->lock);
+		affinity_broken = migrate_one_irq(desc);
+		raw_spin_unlock(&desc->lock);
+
+		if (affinity_broken)
+			pr_warn_ratelimited("IRQ%u no longer affine to CPU%u\n",
+					    i, smp_processor_id());
+	}
+
+	local_irq_restore(flags);
+}
+#endif /* CONFIG_HOTPLUG_CPU */
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 9ba33c40cdf8..cea1594ff933 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -107,7 +107,12 @@ armpmu_map_cache_event(const unsigned (*cache_map)
 static int
 armpmu_map_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
 {
-	int mapping = (*event_map)[config];
+	int mapping;
+
+	if (config >= PERF_COUNT_HW_MAX)
+		return -EINVAL;
+
+	mapping = (*event_map)[config];
 	return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping;
 }
 
@@ -317,7 +322,13 @@ validate_event(struct pmu_hw_events *hw_events,
 	struct hw_perf_event fake_event = event->hw;
 	struct pmu *leader_pmu = event->group_leader->pmu;
 
-	if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF)
+	if (is_software_event(event))
+		return 1;
+
+	if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
+		return 1;
+
+	if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec)
 		return 1;
 
 	return armpmu->get_event_idx(hw_events, &fake_event) >= 0;
@@ -773,7 +784,7 @@ static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 /*
  * PMXEVTYPER: Event selection reg
  */
-#define	ARMV8_EVTYPE_MASK	0xc00000ff	/* Mask for writable bits */
+#define	ARMV8_EVTYPE_MASK	0xc80000ff	/* Mask for writable bits */
 #define	ARMV8_EVTYPE_EVENT	0xff		/* Mask for EVENT bits */
 
 /*
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 46f02c3b5015..4caf198ca44f 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -102,6 +102,13 @@ void arch_cpu_idle(void)
 	local_irq_enable();
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+void arch_cpu_idle_dead(void)
+{
+       cpu_die();
+}
+#endif
+
 void machine_shutdown(void)
 {
 #ifdef CONFIG_SMP
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index 14f73c445ff5..4f97db3d7363 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -17,12 +17,32 @@
 
 #include <linux/init.h>
 #include <linux/of.h>
+#include <linux/smp.h>
 
 #include <asm/compiler.h>
+#include <asm/cpu_ops.h>
 #include <asm/errno.h>
 #include <asm/psci.h>
+#include <asm/smp_plat.h>
 
-struct psci_operations psci_ops;
+#define PSCI_POWER_STATE_TYPE_STANDBY		0
+#define PSCI_POWER_STATE_TYPE_POWER_DOWN	1
+
+struct psci_power_state {
+	u16	id;
+	u8	type;
+	u8	affinity_level;
+};
+
+struct psci_operations {
+	int (*cpu_suspend)(struct psci_power_state state,
+			   unsigned long entry_point);
+	int (*cpu_off)(struct psci_power_state state);
+	int (*cpu_on)(unsigned long cpuid, unsigned long entry_point);
+	int (*migrate)(unsigned long cpuid);
+};
+
+static struct psci_operations psci_ops;
 
 static int (*invoke_psci_fn)(u64, u64, u64, u64);
 
@@ -209,3 +229,68 @@ out_put_node:
 	of_node_put(np);
 	return err;
 }
+
+#ifdef CONFIG_SMP
+
+static int __init cpu_psci_cpu_init(struct device_node *dn, unsigned int cpu)
+{
+	return 0;
+}
+
+static int __init cpu_psci_cpu_prepare(unsigned int cpu)
+{
+	if (!psci_ops.cpu_on) {
+		pr_err("no cpu_on method, not booting CPU%d\n", cpu);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static int cpu_psci_cpu_boot(unsigned int cpu)
+{
+	int err = psci_ops.cpu_on(cpu_logical_map(cpu), __pa(secondary_entry));
+	if (err)
+		pr_err("psci: failed to boot CPU%d (%d)\n", cpu, err);
+
+	return err;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int cpu_psci_cpu_disable(unsigned int cpu)
+{
+	/* Fail early if we don't have CPU_OFF support */
+	if (!psci_ops.cpu_off)
+		return -EOPNOTSUPP;
+	return 0;
+}
+
+static void cpu_psci_cpu_die(unsigned int cpu)
+{
+	int ret;
+	/*
+	 * There are no known implementations of PSCI actually using the
+	 * power state field, pass a sensible default for now.
+	 */
+	struct psci_power_state state = {
+		.type = PSCI_POWER_STATE_TYPE_POWER_DOWN,
+	};
+
+	ret = psci_ops.cpu_off(state);
+
+	pr_crit("psci: unable to power off CPU%u (%d)\n", cpu, ret);
+}
+#endif
+
+const struct cpu_operations cpu_psci_ops = {
+	.name		= "psci",
+	.cpu_init	= cpu_psci_cpu_init,
+	.cpu_prepare	= cpu_psci_cpu_prepare,
+	.cpu_boot	= cpu_psci_cpu_boot,
+#ifdef CONFIG_HOTPLUG_CPU
+	.cpu_disable	= cpu_psci_cpu_disable,
+	.cpu_die	= cpu_psci_cpu_die,
+#endif
+};
+
+#endif
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 6e1e77f1831c..5341534b6d04 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -236,31 +236,29 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type,
 {
 	int err, len, type, disabled = !ctrl.enabled;
 
-	if (disabled) {
-		len = 0;
-		type = HW_BREAKPOINT_EMPTY;
-	} else {
-		err = arch_bp_generic_fields(ctrl, &len, &type);
-		if (err)
-			return err;
-
-		switch (note_type) {
-		case NT_ARM_HW_BREAK:
-			if ((type & HW_BREAKPOINT_X) != type)
-				return -EINVAL;
-			break;
-		case NT_ARM_HW_WATCH:
-			if ((type & HW_BREAKPOINT_RW) != type)
-				return -EINVAL;
-			break;
-		default:
+	attr->disabled = disabled;
+	if (disabled)
+		return 0;
+
+	err = arch_bp_generic_fields(ctrl, &len, &type);
+	if (err)
+		return err;
+
+	switch (note_type) {
+	case NT_ARM_HW_BREAK:
+		if ((type & HW_BREAKPOINT_X) != type)
 			return -EINVAL;
-		}
+		break;
+	case NT_ARM_HW_WATCH:
+		if ((type & HW_BREAKPOINT_RW) != type)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
 	}
 
 	attr->bp_len	= len;
 	attr->bp_type	= type;
-	attr->disabled	= disabled;
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index add6ea616843..85afdae9cc05 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -45,6 +45,7 @@
 #include <asm/cputype.h>
 #include <asm/elf.h>
 #include <asm/cputable.h>
+#include <asm/cpu_ops.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/smp_plat.h>
@@ -97,6 +98,11 @@ void __init early_print(const char *str, ...)
 	printk("%s", buf);
 }
 
+bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
+{
+	return phys_id == cpu_logical_map(cpu);
+}
+
 static void __init setup_processor(void)
 {
 	struct cpu_info *cpu_info;
@@ -269,6 +275,7 @@ void __init setup_arch(char **cmdline_p)
 	psci_init();
 
 	cpu_logical_map(0) = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
+	cpu_read_bootcpu_ops();
 #ifdef CONFIG_SMP
 	smp_init_cpus();
 #endif
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 5d54e3717bf8..35085d664598 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -39,6 +39,7 @@
 #include <asm/atomic.h>
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
+#include <asm/cpu_ops.h>
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -48,13 +49,15 @@
 #include <asm/tlbflush.h>
 #include <asm/ptrace.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/arm-ipi.h>
+
 /*
  * as from 2.5, kernels no longer have an init_tasks structure
  * so we need some other way of telling a new secondary core
  * where to place its SVC stack
  */
 struct secondary_data secondary_data;
-volatile unsigned long secondary_holding_pen_release = INVALID_HWID;
 
 enum ipi_msg_type {
 	IPI_RESCHEDULE,
@@ -63,61 +66,16 @@ enum ipi_msg_type {
 	IPI_CPU_STOP,
 };
 
-static DEFINE_RAW_SPINLOCK(boot_lock);
-
-/*
- * Write secondary_holding_pen_release in a way that is guaranteed to be
- * visible to all observers, irrespective of whether they're taking part
- * in coherency or not.  This is necessary for the hotplug code to work
- * reliably.
- */
-static void __cpuinit write_pen_release(u64 val)
-{
-	void *start = (void *)&secondary_holding_pen_release;
-	unsigned long size = sizeof(secondary_holding_pen_release);
-
-	secondary_holding_pen_release = val;
-	__flush_dcache_area(start, size);
-}
-
 /*
  * Boot a secondary CPU, and assign it the specified idle task.
  * This also gives us the initial stack to use for this CPU.
  */
 static int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
-	unsigned long timeout;
+	if (cpu_ops[cpu]->cpu_boot)
+		return cpu_ops[cpu]->cpu_boot(cpu);
 
-	/*
-	 * Set synchronisation state between this boot processor
-	 * and the secondary one
-	 */
-	raw_spin_lock(&boot_lock);
-
-	/*
-	 * Update the pen release flag.
-	 */
-	write_pen_release(cpu_logical_map(cpu));
-
-	/*
-	 * Send an event, causing the secondaries to read pen_release.
-	 */
-	sev();
-
-	timeout = jiffies + (1 * HZ);
-	while (time_before(jiffies, timeout)) {
-		if (secondary_holding_pen_release == INVALID_HWID)
-			break;
-		udelay(10);
-	}
-
-	/*
-	 * Now the secondary core is starting up let it run its
-	 * calibrations, then wait for it to finish
-	 */
-	raw_spin_unlock(&boot_lock);
-
-	return secondary_holding_pen_release != INVALID_HWID ? -ENOSYS : 0;
+	return -EOPNOTSUPP;
 }
 
 static DECLARE_COMPLETION(cpu_running);
@@ -158,6 +116,11 @@ int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *idle)
 	return ret;
 }
 
+static void __cpuinit smp_store_cpu_info(unsigned int cpuid)
+{
+	store_cpu_topology(cpuid);
+}
+
 /*
  * This is the secondary CPU boot entry.  We're using this CPUs
  * idle thread stack, but a set of temporary page tables.
@@ -187,24 +150,15 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	preempt_disable();
 	trace_hardirqs_off();
 
-	/*
-	 * Let the primary processor know we're out of the
-	 * pen, then head off into the C entry point
-	 */
-	write_pen_release(INVALID_HWID);
+	if (cpu_ops[cpu]->cpu_postboot)
+		cpu_ops[cpu]->cpu_postboot();
 
-	/*
-	 * Synchronise with the boot thread.
-	 */
-	raw_spin_lock(&boot_lock);
-	raw_spin_unlock(&boot_lock);
+	smp_store_cpu_info(cpu);
 
 	/*
-	 * Enable local interrupts.
+	 * Enable GIC and timers.
 	 */
 	notify_cpu_starting(cpu);
-	local_irq_enable();
-	local_fiq_enable();
 
 	/*
 	 * OK, now it's safe to let the boot CPU continue.  Wait for
@@ -214,49 +168,126 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	set_cpu_online(cpu, true);
 	complete(&cpu_running);
 
+	local_irq_enable();
+	local_fiq_enable();
+
 	/*
 	 * OK, it's off to the idle thread for us
 	 */
 	cpu_startup_entry(CPUHP_ONLINE);
 }
 
-void __init smp_cpus_done(unsigned int max_cpus)
+#ifdef CONFIG_HOTPLUG_CPU
+static int op_cpu_disable(unsigned int cpu)
 {
-	unsigned long bogosum = loops_per_jiffy * num_online_cpus();
+	/*
+	 * If we don't have a cpu_die method, abort before we reach the point
+	 * of no return. CPU0 may not have an cpu_ops, so test for it.
+	 */
+	if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_die)
+		return -EOPNOTSUPP;
 
-	pr_info("SMP: Total of %d processors activated (%lu.%02lu BogoMIPS).\n",
-		num_online_cpus(), bogosum / (500000/HZ),
-		(bogosum / (5000/HZ)) % 100);
+	/*
+	 * We may need to abort a hot unplug for some other mechanism-specific
+	 * reason.
+	 */
+	if (cpu_ops[cpu]->cpu_disable)
+		return cpu_ops[cpu]->cpu_disable(cpu);
+
+	return 0;
 }
 
-void __init smp_prepare_boot_cpu(void)
+/*
+ * __cpu_disable runs on the processor to be shutdown.
+ */
+int __cpu_disable(void)
 {
-}
+	unsigned int cpu = smp_processor_id();
+	int ret;
 
-static void (*smp_cross_call)(const struct cpumask *, unsigned int);
+	ret = op_cpu_disable(cpu);
+	if (ret)
+		return ret;
 
-static const struct smp_enable_ops *enable_ops[] __initconst = {
-	&smp_spin_table_ops,
-	&smp_psci_ops,
-	NULL,
-};
+	/*
+	 * Take this CPU offline.  Once we clear this, we can't return,
+	 * and we must not schedule until we're ready to give up the cpu.
+	 */
+	set_cpu_online(cpu, false);
 
-static const struct smp_enable_ops *smp_enable_ops[NR_CPUS];
+	/*
+	 * OK - migrate IRQs away from this CPU
+	 */
+	migrate_irqs();
 
-static const struct smp_enable_ops * __init smp_get_enable_ops(const char *name)
-{
-	const struct smp_enable_ops **ops = enable_ops;
+	/*
+	 * Remove this CPU from the vm mask set of all processes.
+	 */
+	clear_tasks_mm_cpumask(cpu);
+
+	return 0;
+}
 
-	while (*ops) {
-		if (!strcmp(name, (*ops)->name))
-			return *ops;
+static DECLARE_COMPLETION(cpu_died);
 
-		ops++;
+/*
+ * called on the thread which is asking for a CPU to be shutdown -
+ * waits until shutdown has completed, or it is timed out.
+ */
+void __cpu_die(unsigned int cpu)
+{
+	if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) {
+		pr_crit("CPU%u: cpu didn't die\n", cpu);
+		return;
 	}
+	pr_notice("CPU%u: shutdown\n", cpu);
+}
+
+/*
+ * Called from the idle thread for the CPU which has been shutdown.
+ *
+ * Note that we disable IRQs here, but do not re-enable them
+ * before returning to the caller. This is also the behaviour
+ * of the other hotplug-cpu capable cores, so presumably coming
+ * out of idle fixes this.
+ */
+void cpu_die(void)
+{
+	unsigned int cpu = smp_processor_id();
 
-	return NULL;
+	idle_task_exit();
+
+	local_irq_disable();
+
+	/* Tell __cpu_die() that this CPU is now safe to dispose of */
+	complete(&cpu_died);
+
+	/*
+	 * Actually shutdown the CPU. This must never fail. The specific hotplug
+	 * mechanism must perform all required cache maintenance to ensure that
+	 * no dirty lines are lost in the process of shutting down the CPU.
+	 */
+	cpu_ops[cpu]->cpu_die(cpu);
+
+	BUG();
+}
+#endif
+
+void __init smp_cpus_done(unsigned int max_cpus)
+{
+	unsigned long bogosum = loops_per_jiffy * num_online_cpus();
+
+	pr_info("SMP: Total of %d processors activated (%lu.%02lu BogoMIPS).\n",
+		num_online_cpus(), bogosum / (500000/HZ),
+		(bogosum / (5000/HZ)) % 100);
+}
+
+void __init smp_prepare_boot_cpu(void)
+{
 }
 
+static void (*smp_cross_call)(const struct cpumask *, unsigned int);
+
 /*
  * Enumerate the possible CPU set from the device tree and build the
  * cpu logical map array containing MPIDR values related to logical
@@ -264,9 +295,8 @@ static const struct smp_enable_ops * __init smp_get_enable_ops(const char *name)
  */
 void __init smp_init_cpus(void)
 {
-	const char *enable_method;
 	struct device_node *dn = NULL;
-	int i, cpu = 1;
+	unsigned int i, cpu = 1;
 	bool bootcpu_valid = false;
 
 	while ((dn = of_find_node_by_type(dn, "cpu"))) {
@@ -335,25 +365,10 @@ void __init smp_init_cpus(void)
 		if (cpu >= NR_CPUS)
 			goto next;
 
-		/*
-		 * We currently support only the "spin-table" enable-method.
-		 */
-		enable_method = of_get_property(dn, "enable-method", NULL);
-		if (!enable_method) {
-			pr_err("%s: missing enable-method property\n",
-				dn->full_name);
+		if (cpu_read_ops(dn, cpu) != 0)
 			goto next;
-		}
-
-		smp_enable_ops[cpu] = smp_get_enable_ops(enable_method);
 
-		if (!smp_enable_ops[cpu]) {
-			pr_err("%s: invalid enable-method property: %s\n",
-			       dn->full_name, enable_method);
-			goto next;
-		}
-
-		if (smp_enable_ops[cpu]->init_cpu(dn, cpu))
+		if (cpu_ops[cpu]->cpu_init(dn, cpu))
 			goto next;
 
 		pr_debug("cpu logical map 0x%llx\n", hwid);
@@ -383,8 +398,13 @@ next:
 
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
-	int cpu, err;
-	unsigned int ncores = num_possible_cpus();
+	int err;
+	unsigned int cpu, ncores = num_possible_cpus();
+
+	init_cpu_topology();
+
+	smp_store_cpu_info(smp_processor_id());
+
 
 	/*
 	 * are we trying to boot more cores than exist?
@@ -411,10 +431,10 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 		if (cpu == smp_processor_id())
 			continue;
 
-		if (!smp_enable_ops[cpu])
+		if (!cpu_ops[cpu])
 			continue;
 
-		err = smp_enable_ops[cpu]->prepare_cpu(cpu);
+		err = cpu_ops[cpu]->cpu_prepare(cpu);
 		if (err)
 			continue;
 
diff --git a/arch/arm64/kernel/smp_psci.c b/arch/arm64/kernel/smp_psci.c
deleted file mode 100644
index 0c533301be77..000000000000
--- a/arch/arm64/kernel/smp_psci.c
+++ /dev/null
@@ -1,53 +0,0 @@
-/*
- * PSCI SMP initialisation
- *
- * Copyright (C) 2013 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/init.h>
-#include <linux/of.h>
-#include <linux/smp.h>
-
-#include <asm/psci.h>
-#include <asm/smp_plat.h>
-
-static int __init smp_psci_init_cpu(struct device_node *dn, int cpu)
-{
-	return 0;
-}
-
-static int __init smp_psci_prepare_cpu(int cpu)
-{
-	int err;
-
-	if (!psci_ops.cpu_on) {
-		pr_err("psci: no cpu_on method, not booting CPU%d\n", cpu);
-		return -ENODEV;
-	}
-
-	err = psci_ops.cpu_on(cpu_logical_map(cpu), __pa(secondary_holding_pen));
-	if (err) {
-		pr_err("psci: failed to boot CPU%d (%d)\n", cpu, err);
-		return err;
-	}
-
-	return 0;
-}
-
-const struct smp_enable_ops smp_psci_ops __initconst = {
-	.name		= "psci",
-	.init_cpu	= smp_psci_init_cpu,
-	.prepare_cpu	= smp_psci_prepare_cpu,
-};
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 7c35fa682f76..27f08367a6e7 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -16,15 +16,39 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/of.h>
 #include <linux/smp.h>
 
 #include <asm/cacheflush.h>
+#include <asm/cpu_ops.h>
+#include <asm/cputype.h>
+#include <asm/smp_plat.h>
+
+extern void secondary_holding_pen(void);
+volatile unsigned long secondary_holding_pen_release = INVALID_HWID;
 
 static phys_addr_t cpu_release_addr[NR_CPUS];
+static DEFINE_RAW_SPINLOCK(boot_lock);
 
-static int __init smp_spin_table_init_cpu(struct device_node *dn, int cpu)
+/*
+ * Write secondary_holding_pen_release in a way that is guaranteed to be
+ * visible to all observers, irrespective of whether they're taking part
+ * in coherency or not.  This is necessary for the hotplug code to work
+ * reliably.
+ */
+static void write_pen_release(u64 val)
+{
+	void *start = (void *)&secondary_holding_pen_release;
+	unsigned long size = sizeof(secondary_holding_pen_release);
+
+	secondary_holding_pen_release = val;
+	__flush_dcache_area(start, size);
+}
+
+
+static int smp_spin_table_cpu_init(struct device_node *dn, unsigned int cpu)
 {
 	/*
 	 * Determine the address from which the CPU is polling.
@@ -40,7 +64,7 @@ static int __init smp_spin_table_init_cpu(struct device_node *dn, int cpu)
 	return 0;
 }
 
-static int __init smp_spin_table_prepare_cpu(int cpu)
+static int smp_spin_table_cpu_prepare(unsigned int cpu)
 {
 	void **release_addr;
 
@@ -59,8 +83,60 @@ static int __init smp_spin_table_prepare_cpu(int cpu)
 	return 0;
 }
 
-const struct smp_enable_ops smp_spin_table_ops __initconst = {
+static int smp_spin_table_cpu_boot(unsigned int cpu)
+{
+	unsigned long timeout;
+
+	/*
+	 * Set synchronisation state between this boot processor
+	 * and the secondary one
+	 */
+	raw_spin_lock(&boot_lock);
+
+	/*
+	 * Update the pen release flag.
+	 */
+	write_pen_release(cpu_logical_map(cpu));
+
+	/*
+	 * Send an event, causing the secondaries to read pen_release.
+	 */
+	sev();
+
+	timeout = jiffies + (1 * HZ);
+	while (time_before(jiffies, timeout)) {
+		if (secondary_holding_pen_release == INVALID_HWID)
+			break;
+		udelay(10);
+	}
+
+	/*
+	 * Now the secondary core is starting up let it run its
+	 * calibrations, then wait for it to finish
+	 */
+	raw_spin_unlock(&boot_lock);
+
+	return secondary_holding_pen_release != INVALID_HWID ? -ENOSYS : 0;
+}
+
+void smp_spin_table_cpu_postboot(void)
+{
+	/*
+	 * Let the primary processor know we're out of the pen.
+	 */
+	write_pen_release(INVALID_HWID);
+
+	/*
+	 * Synchronise with the boot thread.
+	 */
+	raw_spin_lock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
+}
+
+const struct cpu_operations smp_spin_table_ops = {
 	.name		= "spin-table",
-	.init_cpu 	= smp_spin_table_init_cpu,
-	.prepare_cpu	= smp_spin_table_prepare_cpu,
+	.cpu_init	= smp_spin_table_cpu_init,
+	.cpu_prepare	= smp_spin_table_cpu_prepare,
+	.cpu_boot	= smp_spin_table_cpu_boot,
+	.cpu_postboot	= smp_spin_table_cpu_postboot,
 };
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index d25459ff57fc..048334bb2651 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -48,7 +48,11 @@ int unwind_frame(struct stackframe *frame)
 
 	frame->sp = fp + 0x10;
 	frame->fp = *(unsigned long *)(fp);
-	frame->pc = *(unsigned long *)(fp + 8);
+	/*
+	 * -4 here because we care about the PC at time of bl,
+	 * not where the return will go.
+	 */
+	frame->pc = *(unsigned long *)(fp + 8) - 4;
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
new file mode 100644
index 000000000000..0460ba0573f8
--- /dev/null
+++ b/arch/arm64/kernel/topology.c
@@ -0,0 +1,554 @@
+/*
+ * arch/arm64/kernel/topology.c
+ *
+ * Copyright (C) 2011,2013 Linaro Limited.
+ *
+ * Based on the arm32 version written by Vincent Guittot in turn based on
+ * arch/sh/kernel/topology.c
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/node.h>
+#include <linux/nodemask.h>
+#include <linux/of.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include <asm/topology.h>
+#include <asm/cputype.h>
+#include <asm/smp_plat.h>
+
+
+/*
+ * cpu power scale management
+ */
+
+/*
+ * cpu power table
+ * This per cpu data structure describes the relative capacity of each core.
+ * On a heteregenous system, cores don't have the same computation capacity
+ * and we reflect that difference in the cpu_power field so the scheduler can
+ * take this difference into account during load balance. A per cpu structure
+ * is preferred because each CPU updates its own cpu_power field during the
+ * load balance except for idle cores. One idle core is selected to run the
+ * rebalance_domains for all idle cores and the cpu_power can be updated
+ * during this sequence.
+ */
+static DEFINE_PER_CPU(unsigned long, cpu_scale);
+
+unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu)
+{
+	return per_cpu(cpu_scale, cpu);
+}
+
+static void set_power_scale(unsigned int cpu, unsigned long power)
+{
+	per_cpu(cpu_scale, cpu) = power;
+}
+
+#ifdef CONFIG_OF
+struct cpu_efficiency {
+	const char *compatible;
+	unsigned long efficiency;
+};
+
+/*
+ * Table of relative efficiency of each processors
+ * The efficiency value must fit in 20bit and the final
+ * cpu_scale value must be in the range
+ *   0 < cpu_scale < 3*SCHED_POWER_SCALE/2
+ * in order to return at most 1 when DIV_ROUND_CLOSEST
+ * is used to compute the capacity of a CPU.
+ * Processors that are not defined in the table,
+ * use the default SCHED_POWER_SCALE value for cpu_scale.
+ */
+static const struct cpu_efficiency table_efficiency[] = {
+	{ "arm,cortex-a57", 3891 },
+	{ "arm,cortex-a53", 2048 },
+	{ NULL, },
+};
+
+static unsigned long *__cpu_capacity;
+#define cpu_capacity(cpu)	__cpu_capacity[cpu]
+
+static unsigned long middle_capacity = 1;
+static int cluster_id;
+
+static int __init get_cpu_for_node(struct device_node *node)
+{
+	struct device_node *cpu_node;
+	int cpu;
+
+	cpu_node = of_parse_phandle(node, "cpu", 0);
+	if (!cpu_node) {
+		pr_crit("%s: Unable to parse CPU phandle\n", node->full_name);
+		return -1;
+	}
+
+	for_each_possible_cpu(cpu) {
+		if (of_get_cpu_node(cpu, NULL) == cpu_node)
+			return cpu;
+	}
+
+	pr_crit("Unable to find CPU node for %s\n", cpu_node->full_name);
+	return -1;
+}
+
+static void __init parse_core(struct device_node *core, int core_id)
+{
+	char name[10];
+	bool leaf = true;
+	int i, cpu;
+	struct device_node *t;
+
+	i = 0;
+	do {
+		snprintf(name, sizeof(name), "thread%d", i);
+		t = of_get_child_by_name(core, name);
+		if (t) {
+			leaf = false;
+			cpu = get_cpu_for_node(t);
+			if (cpu >= 0) {
+				pr_info("CPU%d: socket %d core %d thread %d\n",
+					cpu, cluster_id, core_id, i);
+				cpu_topology[cpu].socket_id = cluster_id;
+				cpu_topology[cpu].core_id = core_id;
+				cpu_topology[cpu].thread_id = i;
+			} else {
+				pr_err("%s: Can't get CPU for thread\n",
+				       t->full_name);
+			}
+		}
+		i++;
+	} while (t);
+
+	cpu = get_cpu_for_node(core);
+	if (cpu >= 0) {
+		if (!leaf) {
+			pr_err("%s: Core has both threads and CPU\n",
+			       core->full_name);
+			return;
+		}
+
+		pr_info("CPU%d: socket %d core %d\n",
+			cpu, cluster_id, core_id);
+		cpu_topology[cpu].socket_id = cluster_id;
+		cpu_topology[cpu].core_id = core_id;
+	} else if (leaf) {
+		pr_err("%s: Can't get CPU for leaf core\n", core->full_name);
+	}
+}
+
+static void __init parse_cluster(struct device_node *cluster, int depth)
+{
+	char name[10];
+	bool leaf = true;
+	bool has_cores = false;
+	struct device_node *c;
+	int core_id = 0;
+	int i;
+
+	/*
+	 * First check for child clusters; we currently ignore any
+	 * information about the nesting of clusters and present the
+	 * scheduler with a flat list of them.
+	 */
+	i = 0;
+	do {
+		snprintf(name, sizeof(name), "cluster%d", i);
+		c = of_get_child_by_name(cluster, name);
+		if (c) {
+			parse_cluster(c, depth + 1);
+			leaf = false;
+		}
+		i++;
+	} while (c);
+
+	/* Now check for cores */
+	i = 0;
+	do {
+		snprintf(name, sizeof(name), "core%d", i);
+		c = of_get_child_by_name(cluster, name);
+		if (c) {
+			has_cores = true;
+
+			if (depth == 0)
+				pr_err("%s: cpu-map children should be clusters\n",
+				       c->full_name);
+
+			if (leaf)
+				parse_core(c, core_id++);
+			else
+				pr_err("%s: Non-leaf cluster with core %s\n",
+				       cluster->full_name, name);
+		}
+		i++;
+	} while (c);
+
+	if (leaf && !has_cores)
+		pr_warn("%s: empty cluster\n", cluster->full_name);
+
+	if (leaf)
+		cluster_id++;
+}
+
+/*
+ * Iterate all CPUs' descriptor in DT and compute the efficiency
+ * (as per table_efficiency). Also calculate a middle efficiency
+ * as close as possible to  (max{eff_i} - min{eff_i}) / 2
+ * This is later used to scale the cpu_power field such that an
+ * 'average' CPU is of middle power. Also see the comments near
+ * table_efficiency[] and update_cpu_power().
+ */
+static void __init parse_dt_topology(void)
+{
+	const struct cpu_efficiency *cpu_eff;
+	struct device_node *cn = NULL;
+	unsigned long min_capacity = (unsigned long)(-1);
+	unsigned long max_capacity = 0;
+	unsigned long capacity = 0;
+	int alloc_size, cpu;
+
+	alloc_size = nr_cpu_ids * sizeof(*__cpu_capacity);
+	__cpu_capacity = kzalloc(alloc_size, GFP_NOWAIT);
+
+	cn = of_find_node_by_path("/cpus");
+	if (!cn) {
+		pr_err("No CPU information found in DT\n");
+		return;
+	}
+
+	/*
+	 * If topology is provided as a cpu-map it is essentially a
+	 * root cluster.
+	 */
+	cn = of_find_node_by_name(cn, "cpu-map");
+	if (!cn)
+		return;
+	parse_cluster(cn, 0);
+
+	for_each_possible_cpu(cpu) {
+		const u32 *rate;
+		int len;
+
+		/* Too early to use cpu->of_node */
+		cn = of_get_cpu_node(cpu, NULL);
+		if (!cn) {
+			pr_err("Missing device node for CPU %d\n", cpu);
+			continue;
+		}
+
+		/* check if the cpu is marked as "disabled", if so ignore */
+		if (!of_device_is_available(cn))
+			continue;
+
+		for (cpu_eff = table_efficiency; cpu_eff->compatible; cpu_eff++)
+			if (of_device_is_compatible(cn, cpu_eff->compatible))
+				break;
+
+		if (cpu_eff->compatible == NULL) {
+			pr_warn("%s: Unknown CPU type\n", cn->full_name);
+			continue;
+		}
+
+		rate = of_get_property(cn, "clock-frequency", &len);
+		if (!rate || len != 4) {
+			pr_err("%s: Missing clock-frequency property\n",
+				cn->full_name);
+			continue;
+		}
+
+		capacity = ((be32_to_cpup(rate)) >> 20) * cpu_eff->efficiency;
+
+		/* Save min capacity of the system */
+		if (capacity < min_capacity)
+			min_capacity = capacity;
+
+		/* Save max capacity of the system */
+		if (capacity > max_capacity)
+			max_capacity = capacity;
+
+		cpu_capacity(cpu) = capacity;
+	}
+
+	/* If min and max capacities are equal we bypass the update of the
+	 * cpu_scale because all CPUs have the same capacity. Otherwise, we
+	 * compute a middle_capacity factor that will ensure that the capacity
+	 * of an 'average' CPU of the system will be as close as possible to
+	 * SCHED_POWER_SCALE, which is the default value, but with the
+	 * constraint explained near table_efficiency[].
+	 */
+	if (min_capacity == max_capacity)
+		return;
+	else if (4 * max_capacity < (3 * (max_capacity + min_capacity)))
+		middle_capacity = (min_capacity + max_capacity)
+				>> (SCHED_POWER_SHIFT+1);
+	else
+		middle_capacity = ((max_capacity / 3)
+				>> (SCHED_POWER_SHIFT-1)) + 1;
+
+}
+
+/*
+ * Look for a customed capacity of a CPU in the cpu_topo_data table during the
+ * boot. The update of all CPUs is in O(n^2) for heteregeneous system but the
+ * function returns directly for SMP system.
+ */
+static void update_cpu_power(unsigned int cpu)
+{
+	if (!cpu_capacity(cpu))
+		return;
+
+	set_power_scale(cpu, cpu_capacity(cpu) / middle_capacity);
+
+	pr_info("CPU%u: update cpu_power %lu\n",
+		cpu, arch_scale_freq_power(NULL, cpu));
+}
+
+#else
+static inline void parse_dt_topology(void) {}
+static inline void update_cpu_power(unsigned int cpuid) {}
+#endif
+
+/*
+ * cpu topology table
+ */
+struct cputopo_arm cpu_topology[NR_CPUS];
+EXPORT_SYMBOL_GPL(cpu_topology);
+
+const struct cpumask *cpu_coregroup_mask(int cpu)
+{
+	return &cpu_topology[cpu].core_sibling;
+}
+
+static void update_siblings_masks(unsigned int cpuid)
+{
+	struct cputopo_arm *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
+	int cpu;
+
+	/* update core and thread sibling masks */
+	for_each_possible_cpu(cpu) {
+		cpu_topo = &cpu_topology[cpu];
+
+		if (cpuid_topo->socket_id != cpu_topo->socket_id)
+			continue;
+
+		cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
+		if (cpu != cpuid)
+			cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
+
+		if (cpuid_topo->core_id != cpu_topo->core_id)
+			continue;
+
+		cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling);
+		if (cpu != cpuid)
+			cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
+	}
+	smp_wmb();
+}
+
+void store_cpu_topology(unsigned int cpuid)
+{
+	struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid];
+
+	/* Something should have picked a topology by the time we get here */
+	if (cpuid_topo->core_id == -1)
+		pr_warn("CPU%u: No topology information configured\n", cpuid);
+	else
+		update_siblings_masks(cpuid);
+
+	update_cpu_power(cpuid);
+}
+
+#ifdef CONFIG_SCHED_HMP
+
+/*
+ * Retrieve logical cpu index corresponding to a given MPIDR[23:0]
+ *  - mpidr: MPIDR[23:0] to be used for the look-up
+ *
+ * Returns the cpu logical index or -EINVAL on look-up error
+ */
+static inline int get_logical_index(u32 mpidr)
+{
+	int cpu;
+	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+		if (cpu_logical_map(cpu) == mpidr)
+			return cpu;
+	return -EINVAL;
+}
+
+static const char * const little_cores[] = {
+	"arm,cortex-a53",
+	NULL,
+};
+
+static bool is_little_cpu(struct device_node *cn)
+{
+	const char * const *lc;
+	for (lc = little_cores; *lc; lc++)
+		if (of_device_is_compatible(cn, *lc))
+			return true;
+	return false;
+}
+
+void __init arch_get_fast_and_slow_cpus(struct cpumask *fast,
+					struct cpumask *slow)
+{
+	struct device_node *cn = NULL;
+	int cpu;
+
+	cpumask_clear(fast);
+	cpumask_clear(slow);
+
+	/*
+	 * Use the config options if they are given. This helps testing
+	 * HMP scheduling on systems without a big.LITTLE architecture.
+	 */
+	if (strlen(CONFIG_HMP_FAST_CPU_MASK) && strlen(CONFIG_HMP_SLOW_CPU_MASK)) {
+		if (cpulist_parse(CONFIG_HMP_FAST_CPU_MASK, fast))
+			WARN(1, "Failed to parse HMP fast cpu mask!\n");
+		if (cpulist_parse(CONFIG_HMP_SLOW_CPU_MASK, slow))
+			WARN(1, "Failed to parse HMP slow cpu mask!\n");
+		return;
+	}
+
+	/*
+	 * Else, parse device tree for little cores.
+	 */
+	while ((cn = of_find_node_by_type(cn, "cpu"))) {
+
+		const u32 *mpidr;
+		int len;
+
+		mpidr = of_get_property(cn, "reg", &len);
+		if (!mpidr || len != 8) {
+			pr_err("%s missing reg property\n", cn->full_name);
+			continue;
+		}
+
+		cpu = get_logical_index(be32_to_cpup(mpidr+1));
+		if (cpu == -EINVAL) {
+			pr_err("couldn't get logical index for mpidr %x\n",
+							be32_to_cpup(mpidr+1));
+			break;
+		}
+
+		if (is_little_cpu(cn))
+			cpumask_set_cpu(cpu, slow);
+		else
+			cpumask_set_cpu(cpu, fast);
+	}
+
+	if (!cpumask_empty(fast) && !cpumask_empty(slow))
+		return;
+
+	/*
+	 * We didn't find both big and little cores so let's call all cores
+	 * fast as this will keep the system running, with all cores being
+	 * treated equal.
+	 */
+	cpumask_setall(fast);
+	cpumask_clear(slow);
+}
+
+struct cpumask hmp_slow_cpu_mask;
+
+void __init arch_get_hmp_domains(struct list_head *hmp_domains_list)
+{
+	struct cpumask hmp_fast_cpu_mask;
+	struct hmp_domain *domain;
+
+	arch_get_fast_and_slow_cpus(&hmp_fast_cpu_mask, &hmp_slow_cpu_mask);
+
+	/*
+	 * Initialize hmp_domains
+	 * Must be ordered with respect to compute capacity.
+	 * Fastest domain at head of list.
+	 */
+	if(!cpumask_empty(&hmp_slow_cpu_mask)) {
+		domain = (struct hmp_domain *)
+			kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
+		cpumask_copy(&domain->possible_cpus, &hmp_slow_cpu_mask);
+		cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
+		list_add(&domain->hmp_domains, hmp_domains_list);
+	}
+	domain = (struct hmp_domain *)
+		kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
+	cpumask_copy(&domain->possible_cpus, &hmp_fast_cpu_mask);
+	cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
+	list_add(&domain->hmp_domains, hmp_domains_list);
+}
+#endif /* CONFIG_SCHED_HMP */
+
+/*
+ * cluster_to_logical_mask - return cpu logical mask of CPUs in a cluster
+ * @socket_id:		cluster HW identifier
+ * @cluster_mask:	the cpumask location to be initialized, modified by the
+ *			function only if return value == 0
+ *
+ * Return:
+ *
+ * 0 on success
+ * -EINVAL if cluster_mask is NULL or there is no record matching socket_id
+ */
+int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask)
+{
+	int cpu;
+
+	if (!cluster_mask)
+		return -EINVAL;
+
+	for_each_online_cpu(cpu) {
+		if (socket_id == topology_physical_package_id(cpu)) {
+			cpumask_copy(cluster_mask, topology_core_cpumask(cpu));
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+/*
+ * init_cpu_topology is called at boot when only one cpu is running
+ * which prevent simultaneous write access to cpu_topology array
+ */
+void __init init_cpu_topology(void)
+{
+	unsigned int cpu;
+
+	/* init core mask and power*/
+	for_each_possible_cpu(cpu) {
+		struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]);
+
+		cpu_topo->thread_id = -1;
+		cpu_topo->core_id =  -1;
+		cpu_topo->socket_id = -1;
+		cpumask_clear(&cpu_topo->core_sibling);
+		cpumask_clear(&cpu_topo->thread_sibling);
+
+		set_power_scale(cpu, SCHED_POWER_SCALE);
+	}
+	smp_wmb();
+
+	parse_dt_topology();
+
+	/*
+	 * Assign all remaining CPUs to a cluster so the scheduler
+	 * doesn't get confused.
+	 */
+	for_each_possible_cpu(cpu) {
+		struct cputopo_arm *cpu_topo = &cpu_topology[cpu];
+
+		if (cpu_topo->socket_id == -1) {
+			cpu_topo->socket_id = INT_MAX;
+			cpu_topo->core_id = cpu;
+		}
+	}
+}
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 6a389dc1bd49..0ea7a22bcdf2 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -235,6 +235,8 @@ void update_vsyscall(struct timekeeper *tk)
 	vdso_data->use_syscall			= use_syscall;
 	vdso_data->xtime_coarse_sec		= xtime_coarse.tv_sec;
 	vdso_data->xtime_coarse_nsec		= xtime_coarse.tv_nsec;
+	vdso_data->wtm_clock_sec		= tk->wall_to_monotonic.tv_sec;
+	vdso_data->wtm_clock_nsec		= tk->wall_to_monotonic.tv_nsec;
 
 	if (!use_syscall) {
 		vdso_data->cs_cycle_last	= tk->clock->cycle_last;
@@ -242,8 +244,6 @@ void update_vsyscall(struct timekeeper *tk)
 		vdso_data->xtime_clock_nsec	= tk->xtime_nsec;
 		vdso_data->cs_mult		= tk->mult;
 		vdso_data->cs_shift		= tk->shift;
-		vdso_data->wtm_clock_sec	= tk->wall_to_monotonic.tv_sec;
-		vdso_data->wtm_clock_nsec	= tk->wall_to_monotonic.tv_nsec;
 	}
 
 	smp_wmb();
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index d8064af42e62..6d20b7d162d8 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -48,7 +48,7 @@ $(obj-vdso): %.o: %.S
 
 # Actual build commands
 quiet_cmd_vdsold = VDSOL $@
-      cmd_vdsold = $(CC) $(c_flags) -Wl,-T $^ -o $@
+      cmd_vdsold = $(CC) $(c_flags) -Wl,-n -Wl,-T $^ -o $@
 quiet_cmd_vdsoas = VDSOA $@
       cmd_vdsoas = $(CC) $(a_flags) -c -o $@ $<
 
diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S
index f0a6d10b5211..fe652ffd34c2 100644
--- a/arch/arm64/kernel/vdso/gettimeofday.S
+++ b/arch/arm64/kernel/vdso/gettimeofday.S
@@ -103,6 +103,8 @@ ENTRY(__kernel_clock_gettime)
 	bl	__do_get_tspec
 	seqcnt_check w9, 1b
 
+	mov	x30, x2
+
 	cmp	w0, #CLOCK_MONOTONIC
 	b.ne	6f
 
@@ -118,6 +120,9 @@ ENTRY(__kernel_clock_gettime)
 	ccmp	w0, #CLOCK_MONOTONIC_COARSE, #0x4, ne
 	b.ne	8f
 
+	/* xtime_coarse_nsec is already right-shifted */
+	mov	x12, #0
+
 	/* Get coarse timespec. */
 	adr	vdso_data, _vdso_data
 3:	seqcnt_acquire
@@ -156,7 +161,7 @@ ENTRY(__kernel_clock_gettime)
 	lsr	x11, x11, x12
 	stp	x10, x11, [x1, #TSPEC_TV_SEC]
 	mov	x0, xzr
-	ret	x2
+	ret
 7:
 	mov	x30, x2
 8:	/* Syscall fallback. */
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 3fae2be8b016..2c8a95b539ce 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -41,7 +41,6 @@ SECTIONS
 	}
 	.text : {			/* Real text segment		*/
 		_stext = .;		/* Text and read-only data	*/
-			*(.smp.pen.text)
 			__exception_text_start = .;
 			*(.exception.text)
 			__exception_text_end = .;